File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.jss.2010.11.920
- Scopus: eid_2-s2.0-79751532765
- WOS: WOS:000288142500003
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Testing and validating machine learning classifiers by metamorphic testing
Title | Testing and validating machine learning classifiers by metamorphic testing |
---|---|
Authors | |
Keywords | Validation Test oracle Oracle problem Metamorphic testing Machine learning Verification |
Issue Date | 2011 |
Citation | Journal of Systems and Software, 2011, v. 84, n. 4, p. 544-558 How to Cite? |
Abstract | Machine learning algorithms have provided core functionality to many application domains - such as bioinformatics, computational linguistics, etc. However, it is difficult to detect faults in such applications because often there is no "test oracle" to verify the correctness of the computed outputs. To help address the software quality, in this paper we present a technique for testing the implementations of machine learning classification algorithms which support such applications. Our approach is based on the technique "metamorphic testing", which has been shown to be effective to alleviate the oracle problem. Also presented include a case study on a real-world machine learning application framework, and a discussion of how programmers implementing machine learning algorithms can avoid the common pitfalls discovered in our study. We also conduct mutation analysis and cross-validation, which reveal that our method has high effectiveness in killing mutants, and that observing expected cross-validation result alone is not sufficiently effective to detect faults in a supervised classification program. The effectiveness of metamorphic testing is further confirmed by the detection of real faults in a popular open-source classification program. © 2010 Elsevier Inc. All rights reserved. |
Persistent Identifier | http://hdl.handle.net/10722/262637 |
ISSN | 2023 Impact Factor: 3.7 2023 SCImago Journal Rankings: 1.160 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Xie, Xiaoyuan | - |
dc.contributor.author | Ho, Joshua W.K. | - |
dc.contributor.author | Murphy, Christian | - |
dc.contributor.author | Kaiser, Gail | - |
dc.contributor.author | Xu, Baowen | - |
dc.contributor.author | Chen, Tsong Yueh | - |
dc.date.accessioned | 2018-10-08T02:46:36Z | - |
dc.date.available | 2018-10-08T02:46:36Z | - |
dc.date.issued | 2011 | - |
dc.identifier.citation | Journal of Systems and Software, 2011, v. 84, n. 4, p. 544-558 | - |
dc.identifier.issn | 0164-1212 | - |
dc.identifier.uri | http://hdl.handle.net/10722/262637 | - |
dc.description.abstract | Machine learning algorithms have provided core functionality to many application domains - such as bioinformatics, computational linguistics, etc. However, it is difficult to detect faults in such applications because often there is no "test oracle" to verify the correctness of the computed outputs. To help address the software quality, in this paper we present a technique for testing the implementations of machine learning classification algorithms which support such applications. Our approach is based on the technique "metamorphic testing", which has been shown to be effective to alleviate the oracle problem. Also presented include a case study on a real-world machine learning application framework, and a discussion of how programmers implementing machine learning algorithms can avoid the common pitfalls discovered in our study. We also conduct mutation analysis and cross-validation, which reveal that our method has high effectiveness in killing mutants, and that observing expected cross-validation result alone is not sufficiently effective to detect faults in a supervised classification program. The effectiveness of metamorphic testing is further confirmed by the detection of real faults in a popular open-source classification program. © 2010 Elsevier Inc. All rights reserved. | - |
dc.language | eng | - |
dc.relation.ispartof | Journal of Systems and Software | - |
dc.subject | Validation | - |
dc.subject | Test oracle | - |
dc.subject | Oracle problem | - |
dc.subject | Metamorphic testing | - |
dc.subject | Machine learning | - |
dc.subject | Verification | - |
dc.title | Testing and validating machine learning classifiers by metamorphic testing | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.jss.2010.11.920 | - |
dc.identifier.scopus | eid_2-s2.0-79751532765 | - |
dc.identifier.volume | 84 | - |
dc.identifier.issue | 4 | - |
dc.identifier.spage | 544 | - |
dc.identifier.epage | 558 | - |
dc.identifier.isi | WOS:000288142500003 | - |
dc.identifier.issnl | 0164-1212 | - |